Lifelong Learning from Event-based Data
This work addresses incremental learning challenges for AI agents in dynamic environments, but it appears incremental as it builds on existing techniques for mitigating forgetting.
The paper tackles the problem of catastrophic forgetting in lifelong learning from event-based camera data, proposing a combined model with feature extraction and a habituation-based method to mitigate forgetting, achieving improved retention of previously learned representations.
Lifelong learning is a long-standing aim for artificial agents that act in dynamic environments, in which an agent needs to accumulate knowledge incrementally without forgetting previously learned representations. We investigate methods for learning from data produced by event cameras and compare techniques to mitigate forgetting while learning incrementally. We propose a model that is composed of both, feature extraction and continuous learning. Furthermore, we introduce a habituation-based method to mitigate forgetting. Our experimental results show that the combination of different techniques can help to avoid catastrophic forgetting while learning incrementally from the features provided by the extraction module.